Skip to content

P
pytensor
提交 aff013c8 authored 作者: Brandon T. Willard's avatar Brandon T. Willard 提交者： Thomas Wiecki
浏览文件
操作

Move theano.tensor.nnet.conv2d to theano.tensor.nnet.abstract_conv

上级 9eb77476
隐藏空白字符变更
内嵌 并排
正在显示 包含 276 行增加 和 274 行删除
tests/tensor/nnet/test_abstract_conv.py
浏览文件 @ aff013c8
......@@ -334,7 +334,7 @@ class TestAssertShape:
input = tensor4()
filters = tensor4()
out = conv.conv2d(
out = conv.abstract_conv2d(
input, filters, input_shape=(3, 5, 7, 11), filter_shape=(7, 5, 3, 3)
)
f = theano.function([input, filters], out)
......@@ -888,7 +888,7 @@ class BaseTestConv2d(BaseTestConv):
self,
inputs_shape,
filters_shape,
conv_fn=conv.conv2d,
conv_fn=conv.abstract_conv2d,
conv_op=conv.AbstractConv2d,
ref=conv2d_corr,
**kwargs,
......@@ -1447,7 +1447,7 @@ class TestConvTypes:
out_shape = lvector()
output = conv.conv2d(input, filters)
output = conv.abstract_conv2d(input, filters)
grad_input, grad_filters = theano.grad(output.sum(), wrt=(input, filters))
assert grad_input.type == input.type, (
grad_input,
......@@ -1505,7 +1505,7 @@ class TestConvTypes:
out_shape = lvector()
# Check the forward Op
output = conv.conv2d(constant_tensor, filters)
output = conv.abstract_conv2d(constant_tensor, filters)
grad_filters = theano.grad(output.sum(), wrt=filters)
assert grad_filters.type == filters.type, (
grad_filters,
......@@ -1514,7 +1514,7 @@ class TestConvTypes:
filters.type,
)
output = conv.conv2d(input, constant_tensor)
output = conv.abstract_conv2d(input, constant_tensor)
grad_input = theano.grad(output.sum(), wrt=input)
assert grad_input.type == input.type, (
grad_input,
......
theano/tensor/nnet/__init__.py
浏览文件 @ aff013c8
import warnings
import theano.tensor.nnet.opt
from theano.tensor.nnet.abstract_conv import conv2d as abstract_conv2d
from theano.tensor.nnet.abstract_conv import (
abstract_conv2d,
conv2d,
conv2d_grad_wrt_inputs,
conv2d_transpose,
conv3d,
separable_conv2d,
)
......@@ -49,269 +51,3 @@ from theano.tensor.nnet.sigm import (
softplus,
ultra_fast_sigmoid,
)
def conv2d(
input,
filters,
input_shape=None,
filter_shape=None,
border_mode="valid",
subsample=(1, 1),
filter_flip=True,
image_shape=None,
filter_dilation=(1, 1),
num_groups=1,
unshared=False,
**kwargs,
):
"""
This function will build the symbolic graph for convolving a mini-batch of a
stack of 2D inputs with a set of 2D filters. The implementation is modelled
after Convolutional Neural Networks (CNN).
Parameters
----------
input: symbolic 4D tensor
Mini-batch of feature map stacks, of shape
(batch size, input channels, input rows, input columns).
See the optional parameter ``input_shape``.
filters: symbolic 4D or 6D tensor
Set of filters used in CNN layer of shape
(output channels, input channels, filter rows, filter columns)
for normal convolution and
(output channels, output rows, output columns, input channels,
filter rows, filter columns)
for unshared convolution.
See the optional parameter ``filter_shape``.
input_shape: None, tuple/list of len 4 or 6 of int or Constant variable
The shape of the input parameter.
Optional, possibly used to choose an optimal implementation.
You can give ``None`` for any element of the list to specify that this
element is not known at compile time.
filter_shape: None, tuple/list of len 4 or 6 of int or Constant variable
The shape of the filters parameter.
Optional, possibly used to choose an optimal implementation.
You can give ``None`` for any element of the list to specify that this
element is not known at compile time.
border_mode: str, int or a tuple of two ints or pairs of ints
Either of the following:
``'valid'``: apply filter wherever it completely overlaps with the
input. Generates output of shape: input shape - filter shape + 1
``'full'``: apply filter wherever it partly overlaps with the input.
Generates output of shape: input shape + filter shape - 1
``'half'``: pad input with a symmetric border of ``filter rows // 2``
rows and ``filter columns // 2`` columns, then perform a valid
convolution. For filters with an odd number of rows and columns, this
leads to the output shape being equal to the input shape.
``int``: pad input with a symmetric border of zeros of the given
width, then perform a valid convolution.
``(int1, int2)``: (for 2D) pad input with a symmetric border of ``int1``,
``int2``, then perform a valid convolution.
``(int1, (int2, int3))`` or ``((int1, int2), int3)``: (for 2D)
pad input with one symmetric border of `int1`` or ``int3``, and
one asymmetric border of ``(int2, int3)`` or ``(int1, int2)``.
subsample: tuple of len 2
Factor by which to subsample the output.
Also called strides elsewhere.
filter_flip: bool
If ``True``, will flip the filter rows and columns
before sliding them over the input. This operation is normally referred
to as a convolution, and this is the default. If ``False``, the filters
are not flipped and the operation is referred to as a cross-correlation.
image_shape: None, tuple/list of len 4 of int or Constant variable
Deprecated alias for input_shape.
filter_dilation: tuple of len 2
Factor by which to subsample (stride) the input.
Also called dilation elsewhere.
num_groups : int
Divides the image, kernel and output tensors into num_groups
separate groups. Each which carry out convolutions separately
unshared: bool
If true, then unshared or 'locally connected' convolution will be
performed. A different filter will be used for each region of the
input.
kwargs: Any other keyword arguments are accepted for backwards
compatibility, but will be ignored.
Returns
-------
Symbolic 4D tensor
Set of feature maps generated by convolutional layer. Tensor is
of shape (batch size, output channels, output rows, output columns)
Notes
-----
If cuDNN is available, it will be used on the
GPU. Otherwise, it is the *CorrMM* convolution that will be used
"caffe style convolution".
This is only supported in Theano 0.8 or the development
version until it is released.
The parameter filter_dilation is an implementation of `dilated
convolution <https://arxiv.org/pdf/1511.07122v3.pdf>`_.
"""
if "imshp_logical" in kwargs or "kshp_logical" in kwargs:
raise ValueError(
"Keyword arguments 'imshp_logical' and 'kshp_logical' for conv2d "
"are not supported anymore (and have not been a reliable way to "
"perform upsampling). That feature is still available by calling "
"theano.tensor.nnet.conv.conv2d() for the time being."
)
if len(kwargs.keys()) > 0:
warnings.warn(
str(kwargs.keys()) + " are now deprecated in "
"`tensor.nnet.abstract_conv.conv2d` interface"
" and will be ignored.",
stacklevel=2,
)
if image_shape is not None:
warnings.warn(
"The `image_shape` keyword argument to "
"`tensor.nnet.conv2d` is deprecated, it has been "
"renamed to `input_shape`.",
stacklevel=2,
)
if input_shape is None:
input_shape = image_shape
else:
raise ValueError(
"input_shape and image_shape should not"
" be provided at the same time."
)
return abstract_conv2d(
input,
filters,
input_shape,
filter_shape,
border_mode,
subsample,
filter_flip,
filter_dilation,
num_groups,
unshared,
)
def conv2d_transpose(
input,
filters,
output_shape,
filter_shape=None,
border_mode="valid",
input_dilation=(1, 1),
filter_flip=True,
filter_dilation=(1, 1),
num_groups=1,
unshared=False,
):
"""
This function will build the symbolic graph for applying a transposed
convolution over a mini-batch of a stack of 2D inputs with a set of 2D
filters.
Parameters
----------
input: symbolic 4D tensor
Mini-batch of feature map stacks, of shape
(batch size, input channels, input rows, input columns).
See the optional parameter ``input_shape``.
filters: symbolic 4D tensor
Set of filters used in CNN layer of shape
(input channels, output channels, filter rows, filter columns).
See the optional parameter ``filter_shape``. **Note: the order for
``output_channels`` and ``input_channels`` is reversed with respect to
``conv2d``.**
output_shape: tuple/list of len 4 of int or Constant variable
The shape of the output of ``conv2d_transpose``. The last two elements
are allowed to be ``theano.tensor.type.scalar`` variables.
filter_shape: None, tuple/list of len 4 of int or Constant variable
The shape of the filters parameter.
Optional, possibly used to choose an optimal implementation.
You can give ``None`` for any element of the list to specify that this
element is not known at compile time.
border_mode: str, int or tuple of two int
Refers to the ``border_mode`` argument of the corresponding forward
(non-transposed) convolution. See the argument description in
``conv2d``. What was ``padding`` for the forward convolution means
``cropping`` the output of the transposed one. ``valid`` corresponds to
no cropping, ``full`` to maximal cropping.
input_dilation: tuple of len 2
Corresponds to ``subsample`` (also called strides elsewhere) in the
non-transposed convolution.
filter_flip: bool
If ``True``, will flip the filter rows and columns
before sliding them over the input. This operation is normally referred
to as a convolution, and this is the default. If ``False``, the filters
are not flipped and the operation is referred to as a cross-correlation.
filter_dilation: tuple of len 2
Factor by which to subsample (stride) the input.
Also called dilation elsewhere.
num_groups : int
Divides the image, kernel and output tensors into num_groups
separate groups. Each which carry out convolutions separately
unshared: bool
If true, then unshared or 'locally connected' convolution will be
performed. A different filter will be used for each region of the
input.
Grouped unshared convolution is supported.
Returns
-------
Symbolic 4D tensor
Set of feature maps generated by the transposed convolution. Tensor is
of shape (batch size, output channels, output rows, output columns)
Notes
-----
If cuDNN is available, it will be used on the
GPU. Otherwise, it is the *CorrMM* convolution that will be used
"caffe style convolution".
This operation is also sometimes called "deconvolution".
The parameter filter_dilation is an implementation of `dilated
convolution <https://arxiv.org/pdf/1511.07122v3.pdf>`_.
"""
return conv2d_grad_wrt_inputs(
output_grad=input,
filters=filters,
input_shape=output_shape,
filter_shape=filter_shape,
border_mode=border_mode,
subsample=input_dilation,
filter_flip=filter_flip,
filter_dilation=filter_dilation,
num_groups=num_groups,
unshared=unshared,
)
theano/tensor/nnet/abstract_conv.py
浏览文件 @ aff013c8
......@@ -666,7 +666,7 @@ def border_mode_to_pad(mode, convdim, kshp):
return pad
def conv2d(
def abstract_conv2d(
input,
filters,
input_shape=None,
......@@ -819,7 +819,7 @@ def separable_conv2d(
)[0]
depthwise_op = conv_op(input, depthwise_filters)
pointwise_op = conv2d(
pointwise_op = abstract_conv2d(
input=depthwise_op,
filters=pointwise_filters,
input_shape=depthwise_op_shape,
......@@ -3593,3 +3593,269 @@ class AbstractConv3d_gradInputs(AbstractConv_gradInputs):
d_depth_height_width = (theano.gradient.DisconnectedType()(),)
return (d_weights, d_top) + d_depth_height_width
def conv2d(
input,
filters,
input_shape=None,
filter_shape=None,
border_mode="valid",
subsample=(1, 1),
filter_flip=True,
image_shape=None,
filter_dilation=(1, 1),
num_groups=1,
unshared=False,
**kwargs,
):
"""
This function will build the symbolic graph for convolving a mini-batch of a
stack of 2D inputs with a set of 2D filters. The implementation is modelled
after Convolutional Neural Networks (CNN).
Parameters
----------
input: symbolic 4D tensor
Mini-batch of feature map stacks, of shape
(batch size, input channels, input rows, input columns).
See the optional parameter ``input_shape``.
filters: symbolic 4D or 6D tensor
Set of filters used in CNN layer of shape
(output channels, input channels, filter rows, filter columns)
for normal convolution and
(output channels, output rows, output columns, input channels,
filter rows, filter columns)
for unshared convolution.
See the optional parameter ``filter_shape``.
input_shape: None, tuple/list of len 4 or 6 of int or Constant variable
The shape of the input parameter.
Optional, possibly used to choose an optimal implementation.
You can give ``None`` for any element of the list to specify that this
element is not known at compile time.
filter_shape: None, tuple/list of len 4 or 6 of int or Constant variable
The shape of the filters parameter.
Optional, possibly used to choose an optimal implementation.
You can give ``None`` for any element of the list to specify that this
element is not known at compile time.
border_mode: str, int or a tuple of two ints or pairs of ints
Either of the following:
``'valid'``: apply filter wherever it completely overlaps with the
input. Generates output of shape: input shape - filter shape + 1
``'full'``: apply filter wherever it partly overlaps with the input.
Generates output of shape: input shape + filter shape - 1
``'half'``: pad input with a symmetric border of ``filter rows // 2``
rows and ``filter columns // 2`` columns, then perform a valid
convolution. For filters with an odd number of rows and columns, this
leads to the output shape being equal to the input shape.
``int``: pad input with a symmetric border of zeros of the given
width, then perform a valid convolution.
``(int1, int2)``: (for 2D) pad input with a symmetric border of ``int1``,
``int2``, then perform a valid convolution.
``(int1, (int2, int3))`` or ``((int1, int2), int3)``: (for 2D)
pad input with one symmetric border of `int1`` or ``int3``, and
one asymmetric border of ``(int2, int3)`` or ``(int1, int2)``.
subsample: tuple of len 2
Factor by which to subsample the output.
Also called strides elsewhere.
filter_flip: bool
If ``True``, will flip the filter rows and columns
before sliding them over the input. This operation is normally referred
to as a convolution, and this is the default. If ``False``, the filters
are not flipped and the operation is referred to as a cross-correlation.
image_shape: None, tuple/list of len 4 of int or Constant variable
Deprecated alias for input_shape.
filter_dilation: tuple of len 2
Factor by which to subsample (stride) the input.
Also called dilation elsewhere.
num_groups : int
Divides the image, kernel and output tensors into num_groups
separate groups. Each which carry out convolutions separately
unshared: bool
If true, then unshared or 'locally connected' convolution will be
performed. A different filter will be used for each region of the
input.
kwargs: Any other keyword arguments are accepted for backwards
compatibility, but will be ignored.
Returns
-------
Symbolic 4D tensor
Set of feature maps generated by convolutional layer. Tensor is
of shape (batch size, output channels, output rows, output columns)
Notes
-----
If cuDNN is available, it will be used on the
GPU. Otherwise, it is the *CorrMM* convolution that will be used
"caffe style convolution".
This is only supported in Theano 0.8 or the development
version until it is released.
The parameter filter_dilation is an implementation of `dilated
convolution <https://arxiv.org/pdf/1511.07122v3.pdf>`_.
"""
if "imshp_logical" in kwargs or "kshp_logical" in kwargs:
raise ValueError(
"Keyword arguments 'imshp_logical' and 'kshp_logical' for conv2d "
"are not supported anymore (and have not been a reliable way to "
"perform upsampling). That feature is still available by calling "
"theano.tensor.nnet.conv.conv2d() for the time being."
)
if len(kwargs.keys()) > 0:
warnings.warn(
str(kwargs.keys()) + " are now deprecated in "
"`tensor.nnet.abstract_conv.conv2d` interface"
" and will be ignored.",
stacklevel=2,
)
if image_shape is not None:
warnings.warn(
"The `image_shape` keyword argument to "
"`tensor.nnet.conv2d` is deprecated, it has been "
"renamed to `input_shape`.",
stacklevel=2,
)
if input_shape is None:
input_shape = image_shape
else:
raise ValueError(
"input_shape and image_shape should not"
" be provided at the same time."
)
return abstract_conv2d(
input,
filters,
input_shape,
filter_shape,
border_mode,
subsample,
filter_flip,
filter_dilation,
num_groups,
unshared,
)
def conv2d_transpose(
input,
filters,
output_shape,
filter_shape=None,
border_mode="valid",
input_dilation=(1, 1),
filter_flip=True,
filter_dilation=(1, 1),
num_groups=1,
unshared=False,
):
"""
This function will build the symbolic graph for applying a transposed
convolution over a mini-batch of a stack of 2D inputs with a set of 2D
filters.
Parameters
----------
input: symbolic 4D tensor
Mini-batch of feature map stacks, of shape
(batch size, input channels, input rows, input columns).
See the optional parameter ``input_shape``.
filters: symbolic 4D tensor
Set of filters used in CNN layer of shape
(input channels, output channels, filter rows, filter columns).
See the optional parameter ``filter_shape``. **Note: the order for
``output_channels`` and ``input_channels`` is reversed with respect to
``conv2d``.**
output_shape: tuple/list of len 4 of int or Constant variable
The shape of the output of ``conv2d_transpose``. The last two elements
are allowed to be ``theano.tensor.type.scalar`` variables.
filter_shape: None, tuple/list of len 4 of int or Constant variable
The shape of the filters parameter.
Optional, possibly used to choose an optimal implementation.
You can give ``None`` for any element of the list to specify that this
element is not known at compile time.
border_mode: str, int or tuple of two int
Refers to the ``border_mode`` argument of the corresponding forward
(non-transposed) convolution. See the argument description in
``conv2d``. What was ``padding`` for the forward convolution means
``cropping`` the output of the transposed one. ``valid`` corresponds to
no cropping, ``full`` to maximal cropping.
input_dilation: tuple of len 2
Corresponds to ``subsample`` (also called strides elsewhere) in the
non-transposed convolution.
filter_flip: bool
If ``True``, will flip the filter rows and columns
before sliding them over the input. This operation is normally referred
to as a convolution, and this is the default. If ``False``, the filters
are not flipped and the operation is referred to as a cross-correlation.
filter_dilation: tuple of len 2
Factor by which to subsample (stride) the input.
Also called dilation elsewhere.
num_groups : int
Divides the image, kernel and output tensors into num_groups
separate groups. Each which carry out convolutions separately
unshared: bool
If true, then unshared or 'locally connected' convolution will be
performed. A different filter will be used for each region of the
input.
Grouped unshared convolution is supported.
Returns
-------
Symbolic 4D tensor
Set of feature maps generated by the transposed convolution. Tensor is
of shape (batch size, output channels, output rows, output columns)
Notes
-----
If cuDNN is available, it will be used on the
GPU. Otherwise, it is the *CorrMM* convolution that will be used
"caffe style convolution".
This operation is also sometimes called "deconvolution".
The parameter filter_dilation is an implementation of `dilated
convolution <https://arxiv.org/pdf/1511.07122v3.pdf>`_.
"""
return conv2d_grad_wrt_inputs(
output_grad=input,
filters=filters,
input_shape=output_shape,
filter_shape=filter_shape,
border_mode=border_mode,
subsample=input_dilation,
filter_flip=filter_flip,
filter_dilation=filter_dilation,
num_groups=num_groups,
unshared=unshared,
)
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论